A Methodology to Create Legal Ontologies in a Logic Programming Based Web Information Retrieval System

Abstract

Web legal information retrieval systems need the capability to reason with the knowledge modeled by legal ontologies. Using this knowledge it is possible to represent and to make inferences about the semantic content of legal documents. In this paper a methodology for applying NLP techniques to automatically create a legal ontology is proposed. The ontology is defined in the OWL semantic web language and it is used in a logic programming framework, EVOLP+ISCO, to allow users to query the semantic content of the documents. ISCO allows an easy and efficient integration of declarative, object-oriented and constraint-based programming techniques with the capability to create connections with external databases. EVOLP is a dynamic logic programming framework allowing the definition of rules for actions and events. An application of the proposed methodology to the legal web information retrieval system of the Portuguese Attorney General's Office is described.

Towards a Middle-out Approach for Building Legal Domain Reference Ontology

“…In this approach, the building process of the ontology starts by an analysis and study of relevant information sources about the given domain and then modeling the top level concepts which [2]. This claim is based on the complementary of the two categories which is a fact acknowledged in the literature, specifically in the work of [3], [4] and [6].…”

“…Similar approaches, used to build ontologies in general, are found in the literature and used in the work of [2], [6] and [11]. 1) Francesconi and his colleagues 2008 [2]: proposed a methodology, for multilingual legal knowledge acquisition and modeling, which combines top-down and bottom-up strategies in the work of the DALOS KOS project.…”

“… Bottom-up: use of (semi-)automatic NLP techniques for the knowledge acquisition from texts. 2) Saias and Quaresma [6]: proposed a middle-out, methodology to automatically create a legal ontology from a set of legal documents:  Top-down: Choose an already existent top-level legal ontology.  Bottom-up: Identification of concepts and its properties using NLP techniques.…”

“…Fig. 6 shows our proposed top-down strategy which is constructed in the light of the work of [1] and [6] and organized in five steps. 1) Define a foundational ontology.…”

TULSI: an NLP system for extracting legal modificatory provisions

“…This is the focus of the present work that addresses the problem of semantic annotation of legal texts. In this domain, systems automatically identify and classify structural portions of legal documents and their intra-and inter-references [10,29], and that produce semantic analyses [36,38]. Various initiatives have been established at the national and international levels to devise XML standards that describe legal sources, and to devise schemas that allow encoding such legal documents [24].…”